© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8879
    Prev
    Next
    INDEX
    Explanations

    suddenly or randomly happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unsuccessfully
    -0.11
     confort
    -0.11
     positively
    -0.11
     scrim
    -0.10
    cla
    -0.10
     strugg
    -0.10
    indi
    -0.10
    bate
    -0.10
    ssi
    -0.10
    -strokes
    -0.10
    POSITIVE LOGITS
     suddenly
    0.20
     sudden
    0.16
     abruptly
    0.16
     randomly
    0.14
     simply
    0.14
     arbitrarily
    0.13
     without
    0.13
     spontaneously
    0.13
     abrupt
    0.13
     Suddenly
    0.13
    Activations Density 0.272%

    No Known Activations